RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration

• URL: http://arxiv.org/abs/2309.13257v1
• Date: Sat, 23 Sep 2023 04:41:59 GMT
• Title: RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration
• Authors: Guotian Zeng, Bi Zeng, Hong Zhang, Jianqi Liu and Qingmao Wei
• Abstract summary: Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. This paper proposes RTrack, a novel object representation baseline tracker. RTrack automatically arranges points to define the spatial extents and highlight local areas.
• Score: 3.29854706649876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture the appearance information explicitly and introduces cluttered background. This paper proposes RTrack, a novel object representation baseline tracker that utilizes a set of sample points to get a pseudo bounding box. RTrack automatically arranges these points to define the spatial extents and highlight local areas. Building upon the baseline, we conducted an in-depth exploration of the training potential and introduced a one-to-many leading assignment strategy. It is worth noting that our approach achieves competitive performance to the state-of-the-art trackers on the GOT-10k dataset while reducing training time to just 10% of the previous state-of-the-art (SOTA) trackers' training costs. The substantial reduction in training costs brings single-object tracking (SOT) closer to the object detection (OD) task. Extensive experiments demonstrate that our proposed RTrack achieves SOTA results with faster convergence.

Related papers

• ClickTrack: Towards Real-time Interactive Single Object Tracking [58.52366657445601]
  We propose a new paradigm for single object tracking algorithms, ClickTrack, a new paradigm using clicking interaction for real-time scenarios. To address ambiguity in certain special scenarios, we designed the Guided Click Refiner(GCR), which accepts point and optional textual information as inputs. Experiments on LaSOT and GOT-10k benchmarks show that tracker combined with GCR achieves stable performance in real-time interactive scenarios.
  arXiv  Detail & Related papers  (2024-11-20T10:30:33Z)
• OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning [33.521077115333696]
  We present a general framework to unify various tracking tasks, termed as OneTracker. OneTracker first performs a large-scale pre-training on a RGB tracker called Foundation Tracker. Then we regard other modality information as prompt and build Prompt Tracker upon Foundation Tracker.
  arXiv  Detail & Related papers  (2024-03-14T17:59:13Z)
• Unsupervised Green Object Tracker (GOT) without Offline Pre-training [35.60210259607753]
  We propose a new single object tracking method, called the green object tracker (GOT) GOT offers competitive tracking accuracy with state-of-the-art unsupervised trackers, which demand heavy offline pre-training, at a lower cost. GOT has a tiny model size (3k parameters) and low inference complexity (around 58M FLOPs per frame)
  arXiv  Detail & Related papers  (2023-09-16T19:00:56Z)
• Unifying Tracking and Image-Video Object Detection [54.91658924277527]
  TrIVD (Tracking and Image-Video Detection) is the first framework that unifies image OD, video OD, and MOT within one end-to-end model. To handle the discrepancies and semantic overlaps of category labels, TrIVD formulates detection/tracking as grounding and reasons about object categories.
  arXiv  Detail & Related papers  (2022-11-20T20:30:28Z)
• CXTrack: Improving 3D Point Cloud Tracking with Contextual Information [59.55870742072618]
  3D single object tracking plays an essential role in many applications, such as autonomous driving. We propose CXTrack, a novel transformer-based network for 3D object tracking. We show that CXTrack achieves state-of-the-art tracking performance while running at 29 FPS.
  arXiv  Detail & Related papers  (2022-11-12T11:29:01Z)
• SRRT: Exploring Search Region Regulation for Visual Object Tracking [58.68120400180216]
  We propose a novel tracking paradigm, called Search Region Regulation Tracking (SRRT) SRRT applies a proposed search region regulator to estimate an optimal search region dynamically for each frame. On the large-scale LaSOT benchmark, SRRT improves SiamRPN++ and TransT with absolute gains of 4.6% and 3.1% in terms of AUC.
  arXiv  Detail & Related papers  (2022-07-10T11:18:26Z)
• Unified Transformer Tracker for Object Tracking [58.65901124158068]
  We present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both Single Object Tracking (SOT) and Multiple Object Tracking (MOT)
  arXiv  Detail & Related papers  (2022-03-29T01:38:49Z)
• Learning Target Candidate Association to Keep Track of What Not to Track [100.80610986625693]
  We propose to keep track of distractor objects in order to continue tracking the target. To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision. Our tracker sets a new state-of-the-art on six benchmarks, achieving an AUC score of 67.2% on LaSOT and a +6.1% absolute gain on the OxUvA long-term dataset.
  arXiv  Detail & Related papers  (2021-03-30T17:58:02Z)
• TDIOT: Target-driven Inference for Deep Video Object Tracking [0.2457872341625575]
  In this work, we adopt the pre-trained Mask R-CNN deep object detector as the baseline. We introduce a novel inference architecture placed on top of FPN-ResNet101 backbone of Mask R-CNN to jointly perform detection and tracking. The proposed single object tracker, TDIOT, applies an appearance similarity-based temporal matching for data association.
  arXiv  Detail & Related papers  (2021-03-19T20:45:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.